Somesh Jha

SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification ACL 2026 AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs ICLR 2025 Can Watermarks be Used to Detect LLM IP Infringement For Free? ICLR 2025 CONDA: Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts ICLR 2025 Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks ICLR 2025 On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark AISTATS 2025 Validating Mechanistic Interpretations: An Axiomatic Approach ICML 2025 D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles WACV 2024 Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates ICML 2024 MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance MLHC 2024 On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks ICLR 2024 PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024 Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection ICML 2024 Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs EMNLP 2023 Concept-based Explanations for Out-of-Distribution Detectors ICML 2023 Few-Shot Domain Adaptation For End-to-End Communication ICLR 2023 Grounding Neural Inference with Satisfiability Modulo Theories NeurIPS 2023 Robust and Actively Secure Serverless Collaborative Learning NeurIPS 2023 Stratified Adversarial Robustness with Rejection ICML 2023 The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning ICLR 2023 A Quantitative Geometric Approach to Neural-Network Smoothness NeurIPS 2022 Overparameterization from Computational Constraints NeurIPS 2022 Privacy Implications of Shuffling ICLR 2022 Robust Learning against Relational Adversaries NeurIPS 2022 Towards Evaluating the Robustness of Neural Networks Learned by Transduction ICLR 2022 A General Framework For Detecting Anomalous Inputs to DNN Classifiers ICML 2021 A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks NeurIPS 2021 CaPC Learning: Confidential and Private Collaborative Learning ICLR 2021 Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles NeurIPS 2021 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021 Adversarially Robust Learning Could Leverage Computational Hardness. ALT 2020 CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods ICML 2020 Concise Explanations of Neural Networks using Adversarial Training ICML 2020 Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models ICML 2020 On the Need for Topology-Aware Generative Models for Manifold-Based Defenses ICLR 2020 Attribution-Based Confidence Metric For Deep Neural Networks NeurIPS 2019 Robust Attribution Regularization NeurIPS 2019 Analyzing the Robustness of Nearest Neighbors to Adversarial Examples ICML 2018 Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training ICML 2018